An energy consumption optimization system for remote operation of tower cranes

Abstract

The present invention provides an energy consumption optimization system for remote operation of a tower crane, which relates to the technical field of energy consumption management of tower cranes. The system uses high-precision sensors to collect the motion characteristics, energy trajectories and environmental interference factors of the tower crane in real time, and uses Lie group algebra and Riemann manifolds to achieve unified data representation and feature dimensionality reduction. Energy-sensitive features are extracted through a hierarchical convolutional attention mechanism, a dynamic adversarial body intelligent agent cluster is constructed, the energy relationship of each factor is analyzed, and an energy consumption optimization management strategy is generated. The system realizes cross-modal conversion and gradient utilization through adaptive energy routing, and uses a distributed ledger to record energy conversion efficiency to ensure global energy efficiency balance. The system greatly improves the energy consumption management efficiency of the tower crane, reduces comprehensive energy consumption, and improves energy recovery efficiency, providing a new direction for the green and intelligent development of tower cranes.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management of tower cranes, and in particular to an energy consumption optimization system for remote operation of a tower crane. Background Art

[0002] In the field of tower crane energy management, local energy consumption data is collected through motor current monitoring or mechanical vibration sensors, and energy consumption is evaluated and optimized based on preset rules or empirical formulas. Some attempts have incorporated multi-sensor fusion technology, but these are often limited to simple data superposition or weighted processing, failing to effectively integrate multimodal data. Furthermore, existing energy optimization strategies typically employ fixed thresholds or linear control algorithms, which are difficult to adapt to the complex and changing operating conditions of tower cranes and result in low energy recovery efficiency.

[0003] While existing technologies have improved the accuracy of tower crane energy consumption monitoring to a certain extent, significant flaws remain. The lack of a unified representation method for the fusion of multi-source, heterogeneous data makes it difficult to collaboratively optimize energy flow paths across different modalities. This results in insufficient real-time and adaptable energy consumption management, hindering the further advancement of green construction and intelligent development. Summary of the Invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an energy consumption optimization system for remote operation of a tower crane, comprising:

[0005] The multimodal data fusion module collects the crane's motion characteristics, auxiliary equipment energy trajectory, and environmental interference factors through multi-source sensors, and constructs the crane's first feature tensor;

[0006] The feature processing and analysis module uses a layered convolutional attention mechanism to perform feature extraction and dimensionality reduction on the first feature tensor to extract the second feature tensor of energy-sensitive features;

[0007] The dynamic confrontation module uses the crane motion characteristics, auxiliary equipment energy trajectory, and environmental interference factors in the second feature tensor as multiple participants in the confrontation, constructs an intelligent agent cluster, analyzes the energy relationship and interaction between the participants, and generates an energy consumption optimization management strategy.

[0008] The energy management module establishes an adaptive energy routing topology based on the energy consumption optimization management strategy. By dynamically adjusting the energy flow path, it performs cross-modal conversion and gradient utilization of the mechanical energy, electrical energy, and thermal energy generated by the tower crane under different working conditions.

[0009] The collaborative control module builds a collaborative control mechanism that realizes self-execution of energy scheduling among auxiliary devices through smart contracts and distributed ledger technology, achieving global energy efficiency balance.

[0010] The multimodal data fusion module deploys a high-precision three-axis MEMS inertial sensor array on the tower crane's slewing mechanism, luffing wire rope, and hoisting motor. It uses an AD converter with a sampling frequency of 1kHz to collect the harmonic components of the joint angular acceleration in real time, while extracting the ripple characteristics of the motor's three-phase current. An infrared thermal imager is installed on the surface of the brake friction pad to capture the temperature field gradient distribution at a rate of 30 frames per second. The lidar scans the boom's motion trajectory at a frequency of 10Hz, and the ICP registration point cloud data is used to reconstruct the boom's trajectory envelope. The mechanical vibration signal undergoes multi-scale decomposition using a differentiable wavelet transform, and the Morlet wavelet basis function is used to generate the time-frequency matrix. The time domain window length is dynamically adjusted. The result is a quarter cycle of the main vibration frequency. The thermal image is detected by sliding window using a 7×7 asymmetric convolution kernel. The local overheating area features are extracted by calculating the Laplacian operator response of adjacent pixels. The threshold is set to the ambient temperature + 15°C. The boom motion trajectory is dynamically coupled with the instantaneous wind speed vector measured by the lidar. In the latent space, the mechanical dynamics, thermodynamics and environmental disturbance features are projected onto the manifold through Lie group algebra. The weights of each feature channel are dynamically adjusted through the gated recurrent unit. The weight update period is 100ms. The first feature tensor finally generated has spatiotemporal continuity, with a sampling interval of 50ms in the time dimension and 32 feature channels in the spatial dimension.

[0011] The feature processing and analysis module processes the multimodal data of the tower crane through a hierarchical convolution attention mechanism. At the bottom layer, the convolution layer uses a rotation-sensitive hexagonal topology as the convolution kernel to perform convolution operations on the input feature tensor, so that it can effectively capture the anisotropic vibration modes generated during the swing of the boom. For example, when the tower crane is operating, the vibration amplitude and frequency differences of the boom in different directions are different, thereby extracting low-level features related to mechanical vibration; entering the middle-level processing stage, the dynamic sparse convolution strategy adaptively adjusts the azimuth weight distribution of the convolution kernel according to the real-time changes of the ambient wind speed vector in the first feature tensor. This process dynamically monitors the direction and size changes of the wind speed vector and updates the weight distribution of the convolution kernel in real time to adapt to the influence of wind speed on the vibration mode of the tower crane; at the same time, the dual-stream gating mechanism processes the time domain envelope characteristics and frequency domain harmonic components of the mechanical vibration signal respectively; the time domain and frequency domain characteristics The features are extracted and merged separately to extract the vibration features related to energy consumption; the multi-head attention mechanism at the top level is used to process the thermal imaging temperature gradient field, decompose the thermal imaging temperature gradient field into a radial basis function expansion, and then generate an attention probability map for energy sensitivity by calculating the nonlinear coupling coefficient between each feature channel; this process is similar to finding key feature points related to energy consumption in complex feature data and giving them higher weights to optimize energy consumption more efficiently; in the dimensionality reduction stage, the high-dimensional feature space is compressed to the Riemannian manifold coordinate system derived from the kinematic equation of the boom, by mapping the complex multimodal features to a low-dimensional Riemannian manifold space, while retaining the Jacobian matrix eigenvalue distribution related to environmental interference factors; in this way, the feature processing and analysis module extracts key features closely related to energy consumption optimization from the multimodal data and forms a second feature tensor.

[0012] The dynamic confrontation body module constructs a collaborative optimization agent cluster by assigning the tower crane motion features, auxiliary equipment energy trajectory and environmental interference factors in the second feature tensor to three agents; the agent of the tower crane motion features extracts modes from the harmonic components of mechanical vibration. For example, when the boom swing angle is ±12°, the layered convolutional attention mechanism is used to screen out the vibration component with a main frequency of 2.5Hz and generate corresponding action constraints. These constraints are directly related to the energy loss rate of the boom trajectory envelope. For example, when the vibration amplitude exceeds the threshold, the agent triggers the damping control instruction to suppress the high-frequency jitter at the end of the swing arm and reduce mechanical energy loss. The agent of the energy trajectory updates the priority weight of the energy distribution path based on the spatiotemporal distribution of the thermal imaging temperature gradient field with a period of 0.5 seconds. For example, the area with a temperature gradient exceeding 4℃ / m is marked as a high heat consumption area, and the priority weight is increased to above 0.8. It is then tensor-fused with the energy-sensitive features after dimensionality reduction, such as multiplying the weight matrix element-by-element with the 8-dimensional feature channel in the Riemannian manifold coordinate system to generate an optimized energy distribution strategy. The agent of environmental interference factors generates a compensation coefficient matrix based on the wind speed vector field reconstructed by the lidar and the kinematic parameters of the boom. For example, when the instantaneous wind speed is 7m / s and the direction is at a 45° angle to the boom axis, the wind speed disturbance is mapped to the boom kinematic parameter space through Lie group manifold projection, and the posture deviation of each node is calculated. The compensation coefficient increases nonlinearly along the length of the boom, and the terminal compensation value reaches 1.3 times the baseline value. The communication link between the agents is constructed based on the spatiotemporal continuity characteristics of the first eigentensor, and the interaction weights are 1.3 times the baseline value. Through dynamic adjustment of the covariance matrix between energy-sensitive features, feature channels with covariance values ​​lower than 0.25 are filtered by dynamic sparse convolution; when the amplitude of mechanical energy fluctuation exceeds 15% of the nominal value within 10 seconds, collaborative decision-making is triggered, and the output parameters of each intelligent agent are projected onto the Lie group manifold and orthogonally fused in the tangent space. For example, the thermodynamic gradient weight and the mechanical vibration phase difference are superimposed in a 1:2 ratio, and finally a global strategy is generated that includes energy routing optimization, vibration suppression parameters and environmental compensation, ensuring that the energy efficiency of the tower crane is improved under complex working conditions.

[0013] In the process of generating energy consumption optimization management strategy, each intelligent agent works closely together to generate energy consumption optimization management strategy by analyzing and processing their own characteristic quantities; the intelligent agent of tower crane motion characteristic quantity monitors the change of boom joint torque in real time, and performs covariance analysis with energy sensitive characteristics to generate mechanical energy loss suppression parameters, reflecting the dynamic relationship between torque change and energy loss; the intelligent agent of energy trajectory generates thermodynamic efficiency optimization coefficient based on the spatiotemporal distribution of local overheating areas in the thermal imaging temperature gradient field, combined with the gated attention mechanism, which is used to optimize the energy distribution path and ensure the efficient use of energy in the system; the intelligent agent of environmental interference factor generates energy manifold compensation vector according to the dynamic coupling relationship between the boom trajectory envelope and the wind speed vector, which is used to compensate for the influence of wind speed change on boom motion, thereby reducing energy loss; these parameters are generated by Li The Mann manifold coordinate system is projected and fused to form a dynamic routing table for cross-modal energy conversion; in the dynamic routing table, the conversion priority of mechanical energy and thermal energy is determined by the phase difference between the thermodynamic gradient distribution and the mechanical vibration harmonic component; the system calculates the difference between the phase of the mechanical vibration harmonic component and the phase of the thermodynamic gradient distribution. When the phase difference is small, it indicates that the conversion between mechanical energy and thermal energy is more synchronized, and the priority is higher at this time, and energy conversion is performed first; conversely, when the phase difference is large, the priority is lower, and the system delays or adjusts the energy conversion path to ensure the efficiency and stability of energy conversion; the energy management module adjusts the energy flow path in real time according to the dynamic routing table, and the distributed ledger of the collaborative control module records the energy conversion efficiency characteristics under various working conditions, providing data support for the continuous optimization of the system, thereby realizing efficient energy consumption management of the tower crane under various working conditions.

[0014] When the energy management module constructs the adaptive energy routing topology, the energy flow characteristics of mechanical energy, electrical energy and thermal energy are mapped to the three-dimensional Riemann manifold coordinate system, where mechanical energy corresponds to the rotation component, electrical energy corresponds to the translation component, and thermal energy corresponds to the expansion component. By calculating the vector integral of the energy gradient field, the path with the smallest transmission loss is found as the initial routing topology. The transmission loss is determined by measuring the energy attenuation rate on each path, and the path with an attenuation rate exceeding 15% will be excluded. During the cross-modal conversion process, when the infrared thermal imager detects that the temperature gradient in the brake area exceeds 8°C / m for 5 seconds and the mechanical vibration phase difference is less than π / 9, the conversion path of mechanical energy to thermal energy is automatically activated, and the conversion efficiency is linearly adjusted according to the real-time temperature gradient value. For every 1°C / m increase in the gradient, the efficiency is improved by 3%. The motor phase current ripple characteristics are extracted through spectrum analysis to extract the main harmonic components, and the ripple amplitude is 100%. When the rated value is exceeded by 12%, the electric energy-mechanical energy conversion efficiency is dynamically adjusted at a rate of 0.8% reduction for every 1% ripple amplitude; the layered energy caching strategy divides and stores energy components according to the projection length on the manifold, and energy with a projection length greater than 0.7 is directly driven to execute; energy between 0.4 and 0.7 is stored in the cache; energy less than 0.4 is transferred to backup energy storage; energy decomposition uses orthogonalization processing on the manifold to decompose the mechanical energy generated by the boom swing into three non-interfering components, and the storage priority of each component is determined by its modulus in the manifold coordinate system; dynamic adjustment of routing topology is achieved through real-time monitoring of the energy manifold distortion index in the second eigenvalue tensor. When the distortion index exceeds the threshold due to the ambient wind speed, the system completes path reconstruction within 100ms. The new path ensures that the energy transmission efficiency of each node is not low, and the path change record is written to the distributed ledger.

[0015] When the collaborative control module constructs a distributed ledger, the conversion records of mechanical energy, electrical energy, and thermal energy are stored in the nodes respectively. Each node receives the second feature tensor data at intervals of 0.1 seconds, and establishes energy conversion priority rules by analyzing the mechanical vibration harmonic components and the thermal imaging temperature gradient field. When the rules are generated, when the correlation coefficient between the 2.5Hz vibration component and the temperature gradient field is detected to be greater than 0.7, the working condition is automatically marked as a priority processing scenario. The bottom-level verification node compares the matching degree of the energy flow path with the preset topology in real time and calculates the similarity. An alarm is triggered when the matching degree is lower than 85%. The upper-level verification node verifies energy conservation through Lie group manifold projection, and determines it as an abnormality when the input and output energy deviation exceeds 5%. The energy redistribution process selects the optimal solution from the rule table and completes the adjustment within 200ms after double-layer verification. When the ledger is updated, each node verifies the data consistency through feature hashing to ensure that the records are authentic and reliable.

[0016] The present invention provides an energy consumption optimization system for remote operation of a tower crane, which has the following beneficial effects:

[0017] 1. The present invention significantly improves the energy consumption management efficiency in remote tower crane operation through multimodal data fusion and intelligent collaborative optimization mechanism; through the collaborative decision-making of layered convolutional attention mechanism and dynamic opponent antibody cluster, it captures the operating status and energy flow characteristics of the tower crane in real time, thereby generating an optimization strategy that adapts to complex working conditions and effectively reduces the overall energy consumption.

[0018] 2. The present invention achieves efficient cross-modal energy conversion and gradient utilization through adaptive energy routing topology, significantly improving energy recovery efficiency. The system dynamically triggers the optimal energy distribution path based on energy characteristics, reducing energy waste, while also lowering the risk of wear of key components and extending the service life of the equipment.

[0019] 3. The present invention realizes the automation and transparency of energy scheduling among auxiliary equipment, which not only improves the intelligence level of remote operation of tower cranes, but also provides industrial application value and social and economic benefits for green construction and sustainable energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] An energy consumption optimization system for remote operation of a tower crane achieves refined energy consumption management of the tower crane under complex working conditions through five core modules: multimodal data fusion, feature processing and analysis, dynamic confrontation body optimization, adaptive energy routing, and distributed collaborative control.

[0023] A high-precision sensor array was deployed in the tower crane, including three-axis MEMS inertial sensors at the slewing mechanism, luffing wire rope, and hoisting motor. The sampling frequency was set to 1 kHz, which was used to collect the harmonic components of the joint angular acceleration and the motor's three-phase current ripple characteristics in real time. An infrared thermal imager mounted on the brake friction pad captured the temperature field gradient distribution at a rate of 30 frames per second, and a lidar scanned the boom trajectory at a frequency of 10 Hz. The boom trajectory envelope was reconstructed through ICP registration. The mechanical vibration signal was processed using a differentiable wavelet transform, with Morlet wavelet basis functions used for multi-scale decomposition. The time domain window was dynamically adjusted to 1 / 4 period of the main vibration frequency to generate a matrix containing time-frequency information. The thermal image was detected using a 7×7 asymmetric convolution kernel sliding detection, extracting local overheating area features with a threshold set to the ambient temperature + 15°C. A dynamic coupling relationship was established between the boom motion trajectory and the instantaneous wind speed vector measured by the lidar.

[0024] The system projects the mechanical dynamic characteristics, thermodynamic characteristics and environmental disturbance characteristics onto a unified manifold through Lie group algebra. Specifically, the rotational motion of the boom is represented as elements on the SO(3) Lie group, and the translational motion is represented as elements on the SE(3) Lie group. Through exponential mapping, the angular velocity and linear velocity of the mechanical vibration are converted into corresponding group elements, so that different modal data can be fused under a unified framework. The gated recurrent unit updates the weight every 100ms, dynamically adjusts the contribution of each feature channel, and finally generates a first feature tensor that is continuous in time and space. The sampling interval of the time dimension is 50ms, and the spatial dimension contains 32 feature channels.

[0025] The hierarchical convolution attention mechanism performs in-depth processing on the first feature tensor; the bottom convolution layer uses a rotation-sensitive hexagonal topology as the convolution kernel to effectively capture the anisotropic vibration mode generated by the boom swing; in the middle-level processing stage, the dynamic sparse convolution strategy adaptively adjusts the azimuth weight distribution of the convolution kernel according to the real-time wind speed vector; when the angle between the wind speed direction and the boom axis exceeds 30° and the wind speed exceeds 5m / s, the corresponding azimuth weight is increased by 20%; the dual-stream gating mechanism processes the time domain envelope and frequency domain harmonics of the mechanical vibration signal respectively, and generates comprehensive features through element-level fusion; the top-level multi-head attention mechanism converts the thermal imaging temperature gradient field into the thermal image temperature gradient field. It is decomposed into a radial basis function expansion to calculate the nonlinear coupling coefficient between each characteristic channel; for example, when the coupling coefficient between a certain area in the temperature gradient field and the adjacent area exceeds 0.6, the area is marked as an energy-sensitive area; the high-dimensional feature space is compressed to 8 dimensions through the Riemannian manifold coordinate system while retaining the eigenvalue distribution of the Jacobian matrix; the implementation of the Riemannian manifold is based on the kinematic equation of the boom, and the eigenvectors of mechanical energy, thermal energy and electrical energy are mapped into a unified manifold space; by calculating the geodesic distance between the eigenvectors, the similarity between different energy modes is determined, thereby achieving feature dimensionality reduction; and finally a second eigentensor is formed.

[0026] The crane motion characteristic quantities, auxiliary equipment energy trajectory and environmental interference factors in the second characteristic tensor are assigned to three intelligent agents to build a collaborative optimization cluster. The crane motion characteristic quantity intelligent agent generates damping control parameters by analyzing the harmonic components of mechanical vibration when the boom swing angle exceeds ±10° and the vibration frequency exceeds 2Hz, suppressing terminal jitter and reducing the mechanical energy loss rate by 18%. The energy trajectory intelligent agent is based on the thermal imaging temperature gradient field. When the temperature gradient in the brake area exceeds 6℃ / m, the priority weight is increased to 0.7, and tensor fusion is performed with the energy-sensitive features. The environmental interference intelligent agent uses the wind speed vector field reconstructed by the lidar to generate a compensation coefficient matrix when the instantaneous wind speed exceeds 6m / s and the angle between the direction and the boom exceeds 30°. The wind speed disturbance is mapped to the boom kinematic parameter space through Lie group manifold projection. The terminal compensation value reaches 1.2 times the baseline value, ensuring the stability of the boom trajectory.

[0027] The communication link between intelligent agents is constructed based on the spatiotemporal continuity of the characteristic tensor, and the interaction weights are dynamically adjusted through the covariance matrix; when the amplitude of mechanical energy fluctuation exceeds 15% of the nominal value within 10 seconds, collaborative decision-making is triggered, and the output parameters of each intelligent agent are orthogonally fused in the tangent space to generate a global energy consumption optimization strategy; during the fusion process, the interaction between Lie group manifolds and Riemann manifolds is reflected in the following: Lie group manifolds provide the transformation basis of kinematic parameters, while Riemann manifolds determine the priority of energy conversion through geodesic optimization; for example, when the phase difference between the mechanical vibration and the thermodynamic gradient is less than π / 6, the system determines that the energy conversion synchronization is high and preferentially triggers the conversion path of mechanical energy to thermal energy.

[0028] The adaptive energy routing topology maps the energy flow characteristics of mechanical energy, electrical energy, and thermal energy into a three-dimensional Riemannian manifold coordinate system, where mechanical energy corresponds to the rotational component, electrical energy corresponds to the translational component, and thermal energy corresponds to the expansion and contraction component. By calculating the vector integral of the energy gradient field, the path with the smallest transmission loss is found as the initial topology. When the energy attenuation rate of the path exceeds 15%, it is automatically excluded to ensure energy transmission efficiency. During the cross-modal conversion process, when the infrared thermal imager detects that the temperature gradient in the brake area exceeds 8°C / m for 5 seconds and the mechanical vibration phase difference is less than π / 6, the conversion path from mechanical energy to thermal energy is activated, and the conversion efficiency is linearly adjusted with the temperature gradient, with the efficiency increasing by 2% for every 1°C / m increase.

[0029] The hierarchical energy caching strategy prioritizes storage based on the projection length of the energy component on the manifold. Energy with a projection length greater than 0.6 is directly driven for execution, energy between 0.3 and 0.6 is stored in the cache, and energy less than 0.3 is transferred to backup energy storage. Energy decomposition uses manifold orthogonalization to decompose the boom swing mechanical energy into three non-interfering components, and the storage priority of each component is determined by the module length. When the ambient wind speed causes the energy manifold distortion index to exceed 0.2, the system completes path reconstruction within 100ms to ensure that the transmission efficiency of each node is not less than 85%. During the reconstruction process, the Lie group manifold is used to update the compensation coefficient of the boom kinematic parameters, while the Riemann manifold determines the new energy flow path through geodesic replanning.

[0030] The distributed ledger uses energy conversion efficiency as its consensus mechanism, and the conversion records of mechanical energy, electrical energy, and thermal energy are stored in different nodes respectively; each node receives the second characteristic tensor data at intervals of 0.1 seconds, analyzes the mechanical vibration harmonics and the temperature gradient field, and establishes energy conversion priority rules; for example, when the correlation coefficient between the 2.5Hz vibration component and the temperature gradient field exceeds 0.6, the working condition is marked as a priority processing scenario; the bottom-level verification node compares the matching degree of the energy flow path with the preset topology in real time, and triggers an alarm when the matching degree is less than 80%; the upper-level verification node verifies energy conservation through Lie group manifold projection, and determines it as an abnormality when the input and output energy deviation exceeds 3%; the energy redistribution process selects the optimal solution from the rule table, and completes the adjustment within 200ms after double-layer verification.

[0031] For example, in a tower crane operation scenario at a construction site, when the instantaneous wind speed reaches 7m / s and its direction forms a 45° angle with the boom, the environmental interference agent generates a compensation coefficient matrix to map the wind speed disturbance to the boom kinematic parameter space; at this time, the tower crane motion feature agent detects that the boom swing angle exceeds ±12° and the vibration frequency reaches 2.8Hz, and generates damping control parameters to suppress terminal jitter; the energy trajectory agent detects that the brake temperature gradient exceeds 8°C / m, and the priority weight is increased to 0.8, triggering the conversion path of mechanical energy to thermal energy, and the conversion efficiency is improved to 83%; the system fuses the parameters of each agent through the Riemannian manifold coordinate system to generate a dynamic routing table, setting the priority of mechanical energy to thermal energy conversion to the highest; the energy management module adjusts the energy flow path according to the routing table, converts excess mechanical energy into thermal energy storage, and records the energy conversion efficiency characteristics through the distributed ledger; the collaborative control module verifies that the energy distribution path matches the preset topology at a degree of match of 92%, and the energy conservation verification deviation is controlled within 1.5% to ensure global energy efficiency balance.

[0032] In the system, Lie group manifolds and Riemann manifolds are responsible for processing the continuous symmetry and transformation of the dynamic system, providing a mathematical basis for the kinematic parameters of the boom; Riemann manifolds achieve unified representation and efficient conversion of multimodal energy characteristics through geodesic optimization and feature dimensionality reduction; the two work together to ensure that the system achieves refined control of energy consumption optimization and energy management under complex working conditions; for example, under complex wind conditions, the system reduces the overall energy consumption of the tower crane, improves energy recovery efficiency, and reduces wear on key components; distributed ledger records show that the standard deviation of the energy conversion efficiency characteristics is reduced and the system stability is improved; through the mathematical mapping of Lie group manifolds and Riemann manifolds, the unified representation and efficient conversion of multimodal energy characteristics are achieved, providing reliable technical support for the green and intelligent development of remote operation of tower cranes.

[0033] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An energy consumption optimization system for remote operation of a tower crane, characterized in that: include: The multimodal data fusion module collects the crane's motion characteristics, auxiliary equipment energy trajectory, and environmental interference factors through multi-source sensors, and constructs the crane's first feature tensor; The feature processing and analysis module uses a layered convolutional attention mechanism to perform feature extraction and dimensionality reduction on the first feature tensor to extract the second feature tensor of energy-sensitive features; The dynamic confrontation module uses the crane motion characteristics, auxiliary equipment energy trajectory, and environmental interference factors in the second feature tensor as multiple participants in the confrontation, constructs an intelligent agent cluster, analyzes the energy relationship and interaction between the participants, and generates an energy consumption optimization management strategy. The energy management module establishes an adaptive energy routing topology based on the energy consumption optimization management strategy. By dynamically adjusting the energy flow path, it performs cross-modal conversion and gradient utilization of the mechanical energy, electrical energy, and thermal energy generated by the tower crane under different working conditions. The collaborative control module builds a collaborative control mechanism that realizes self-execution of energy scheduling among auxiliary devices through smart contracts and distributed ledger technology, achieving global energy efficiency balance.

2. The energy consumption optimization system for remote tower crane operation according to claim 1, characterized in that: The multimodal data fusion module deploys a three-axis MEMS inertial sensor array on the tower crane's slewing mechanism, luffing wire rope, and hoisting motor. This module collects the harmonic components of the joint angular acceleration and the motor phase current ripple characteristics in real time. An infrared thermal imager captures the temperature gradient distribution of the brake friction pad and reconstructs the boom trajectory envelope using lidar point cloud data. A differentiable wavelet transform is used to perform multi-scale decomposition of the mechanical vibration signal to obtain a time-frequency matrix. Morlet wavelet basis functions are used, and the time domain window length is dynamically adjusted to one-quarter of the vibration main frequency. An asymmetric convolution kernel is used to extract the characteristics of local overheating areas in the thermal image and establish a dynamic coupling relationship between the boom motion and the wind speed vector. Finally, in the latent space, the mechanical dynamics, thermodynamics, and environmental disturbance characteristics are projected onto a unified Lie group manifold to form a first feature tensor with spatiotemporal continuity. The contribution weight of each feature channel is dynamically adjusted through a gated recurrent unit to achieve noise suppression and feature complementarity.

3. The energy consumption optimization system for remote tower crane operation according to claim 2, characterized in that: The feature processing and analysis module uses a layered convolutional attention mechanism to construct a cascade processing structure consisting of spatiotemporal interleaved convolution layers and gated attention units. The bottom convolution kernel uses a rotation-sensitive hexagonal topology to capture the anisotropic vibration modes of the boom swing. The middle layer uses a dynamic sparse convolution strategy to adaptively adjust the azimuth weight distribution of the convolution kernel according to the real-time changes of the ambient wind speed vector in the first feature tensor, and uses a dual-stream gating mechanism to separately process the time domain envelope characteristics and frequency domain harmonic components of the mechanical vibration signal. The top-level design uses a multi-head attention mechanism with energy-aware capabilities. It decomposes the thermal imaging temperature gradient field into a radial basis function expansion and generates an energy-sensitive attention probability map by calculating the nonlinear coupling coefficients between each feature channel. In the dimensionality reduction stage, the high-dimensional feature space is compressed to the Riemannian manifold coordinate system derived from the kinematic equations of the boom, while retaining the eigenvalue distribution of the Jacobian matrix related to the environmental interference factors, and finally forming the second eigentensor.

4. The energy consumption optimization system for remote tower crane operation according to claim 3, characterized in that: The dynamic pairing module constructs an agent cluster, in which the tower crane motion feature, the auxiliary equipment energy trajectory, and the environmental interference factor in the second feature tensor are assigned to three agents. The tower crane motion feature agent generates action constraints based on the mechanical vibration harmonic components extracted by the layered convolutional attention mechanism, and its output is associated with the energy loss rate of the boom swing trajectory envelope. The energy trajectory agent predicts the priority weights of the energy distribution path based on the thermal imaging temperature gradient field constructed by the multimodal data fusion module and fuses the weights with the second feature tensor. The intelligent agent of environmental interference factors uses the wind speed vector field reconstructed by lidar to generate a compensation coefficient matrix linked to the kinematic parameters of the boom. This matrix is ​​aligned with the mechanical vibration characteristics through Lie group manifold projection. The communication links between the agents are constructed based on the spatiotemporal continuity characteristics of the first feature tensor. The interaction weights are adjusted by the correlation between energy-sensitive features extracted from the hierarchical convolutional attention mechanism. Noise signals irrelevant to the current working conditions are filtered out through dynamic sparse convolution, so that the agents trigger collaborative decision-making only when the mechanical energy fluctuation threshold is exceeded.

5. The energy consumption optimization system for remote tower crane operation according to claim 4, characterized in that: The energy consumption optimization management strategy is generated by using an intelligent agent that calculates the covariance matrix of the boom joint torque and energy-sensitive characteristics in real time through the tower crane motion feature quantity to generate mechanical energy loss suppression parameters. The energy trajectory intelligent agent generates a thermodynamic efficiency optimization coefficient based on the spatiotemporal distribution of local overheating areas in the thermal imaging temperature gradient field, combined with a gated attention mechanism. The environmental interference agent generates an energy manifold compensation vector based on the dynamic coupling relationship between the boom trajectory envelope and the wind speed vector; the above parameters are projected and fused through the Riemannian manifold coordinate system to form a dynamic routing table for cross-modal energy conversion, where the conversion priority of mechanical energy and thermal energy is determined by the phase difference between the thermodynamic gradient distribution and the harmonic component of the mechanical vibration; finally, the energy consumption optimization management strategy adjusts the energy flow path in real time through the adaptive routing topology of the energy management module, and uses the distributed ledger of the collaborative control module to record the energy conversion efficiency characteristics under various working conditions.

6. The energy consumption optimization system for remote tower crane operation according to claim 5, characterized in that: The energy management module implements an adaptive energy routing topology to map the energy flow characteristics of mechanical energy, electrical energy and thermal energy into a Riemannian manifold coordinate system, and constructs an initial routing topology by solving the optimal transmission path of the energy gradient field; For the cross-modal conversion process, a bidirectional gating mechanism based on thermodynamic gradient distribution and mechanical vibration phase difference is designed. When the thermal imaging temperature gradient exceeds the threshold, the conversion path of mechanical energy to thermal energy is triggered, and the conversion efficiency of electrical energy and mechanical energy is dynamically adjusted according to the motor phase current ripple characteristics; in the gradient utilization stage, the excess mechanical energy generated by the swing of the boom is decomposed into energy components of different priorities through Lie group manifold projection through a layered energy caching strategy. The high-priority components are directly supplied to the current working conditions, and the low-priority components are stored in the energy pool; the dynamic adjustment of the routing topology is achieved by real-time monitoring of the second feature tensor output by the feature processing and analysis module. When the energy manifold is distorted by environmental interference factors, the routing path is immediately reconstructed and the energy distribution record in the distributed ledger is updated.

7. The energy consumption optimization system for remote tower crane operation according to claim 6, characterized in that: The collaborative control module constructs a distributed ledger based on an adaptive routing topology with energy conversion efficiency as the consensus mechanism. Each sub-chain in the distributed ledger corresponds to a conversion record of an energy mode; the conversion records of mechanical energy, electrical energy, and thermal energy are respectively stored in different nodes; by analyzing the mechanical vibration harmonic components and the thermal imaging temperature gradient field in the second eigentensor, an energy conversion priority rule table is established. When the envelope surface of the boom swing trajectory does not match the energy demand of the current working condition, the energy redistribution process is automatically triggered; a two-layer verification mechanism is adopted, in which the bottom-level verification node compares the matching degree of the actual energy flow path with the routing topology in real time, and the upper-level verification node evaluates the global efficiency through the energy conservation constraint on the Lie group manifold.

Images